self-evolving-crm
Warn
Audited by Snyk on Jun 21, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). 在每日定时工作流的 Step 1(Data Collector)中,技能会通过 Gmail API 读取用户收发邮件正文/片段(body_snippet)并将其作为 LLM 输入的 raw_interaction_records;这些邮件内容属于“Gmail 中非用户本人撰写的外部通信正文”,属于外部自由文本来源。
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata